Automatically initialized local active contour model heart and cerebral vessel segmentation method

Abstract

The invention provides an automatically initialized local active contour model heart and cerebral vessel segmentation method. The method comprises the following steps: performing anisotropic filtering on a three-dimensional vessel according to the tubular feature of the vessel in medical image data to acquire an initial contour line; constructing a local energy function; minimizing the local energy function by a gradient descent method to acquire the corresponding gradient descent flow; constructing a vessel vector field according to the vessel shape measurement of the medical image data; and finally combining the gradient descent flow and the vessel vector field to acquire a vessel evolution equation. The method can automatically set the initial contour line according to the vessel shape and is precise in segmentation, high in efficiency and high in robustness.

Description

technical field [0001] The invention relates to the field of computer application technology, in particular to a method for segmenting blood vessels by using a local active contour model and a blood vessel vector field, which is mainly used in the fields of medical teaching and calculation-aided diagnosis and treatment. Background technique [0002] At present, cardiovascular and cerebrovascular diseases have become the "first killer" of human health. The number of people who die from cardiovascular and cerebrovascular diseases in the world is as high as 15 million every year. In China, there are more than 270 million patients with cardiovascular and cerebrovascular diseases, and nearly 3 million people die from cardiovascular and cerebrovascular diseases every year, accounting for 51% of the total number of deaths. Among the surviving patients, 75% lost their ability to work to varying degrees, and 40% were seriously disabled. [0003] Cardiovascular and cerebrovascular di...

AI Technical Summary

Problems solved by technology

For the problem of uneven gray distribution of blood vessels, especially small blood vessels, it is difficult to accurately segment

In the process of contour line evolution in the current method, usually all pixels in the image domain participate in the calculation, and the calculation load is large

In addition, the traditional blood vessel segmentation method based on the geometric active contour model is easy to fall into the local minimum, and the setting requirements for the initial contour line are relatively strict.

Images